© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128785
    Prev
    Next
    INDEX
    Explanations

    This neuron detects capitalized multiword identifiers or titles—especially CamelCase names such as class or section headings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references, technical codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     with
    -1.07
     but
    -0.96
     new
    -0.95
    dji
    -0.92
    だが
    -0.91
    <bos>
    -0.90
     саны
    -0.90
    angkap
    -0.90
    indonesia
    -0.86
     pintura
    -0.85
    POSITIVE LOGITS
    ts
    1.09
    つづく
    1.08
    再一次
    1.01
     différentes
    1.00
     ſever
    0.98
    ほら
    0.96
     visse
    0.96
    事が
    0.95
    がっ
    0.93
    rt
    0.93
    Activations Density 0.039%

    No Known Activations